FNN-based tensor heterogeneous integrated Internet of Vehicles missing data estimation method

Abstract

The invention discloses an FNN-based tensor heterogeneous integrated Internet of Vehicles missing data estimation method. Traffic condition information is obtained by the Internet of Vehicles througha large amount of data collected by sensors. However, low-quality problems such as data loss and abnormal data always seriously restrict the development and application of the Internet of Vehicles. According to the FNNTEL method, robust missing data reduction is carried out on a space-time multi-dimensional data set for the problems of large road network data missing and low-quality abnormity, anda new tensor decomposition data sampling strategy is adopted; a heterogeneous integration idea is introduced into traffic data reduction modeling for the first time, and a tensor decomposition heterogeneous integration model is constructed, so that the multi-dimensionality of traffic data can be reserved, and multi-mode association of a bottom layer can be extracted; and optimizing the model by using the fuzzy neural network. Compared with relatively advanced algorithms such as BGCP, HTD and XalRTC in recent years, the FNNTEL method has the advantages that the data missing reconstruction capability is improved, the data interpolation error is reduced, and the reduction precision is effectively improved.

Description

technical field [0001] The invention belongs to the field of Internet of Things and big data processing, and in particular relates to an FNN-based tensor heterogeneous integration vehicle networking missing data estimation method. Background technique [0002] With the rapid development of Internet of Vehicles (IOV) and sensor technology, a large amount of urban traffic data is continuously collected by fixed or mobile sensors in the road network such as loop detectors, microwave detectors, and floating vehicles. It is used to capture the basic status and dynamics of the traffic road network to form multi-dimensional traffic big data. However, due to the limited spatial range of fixed sensors, mobile sensors have highly unstable spatial and temporal resolutions. At the same time, the data set collection process is often accompanied by factors such as sensor failure or transmission distortion, which inevitably lead to loss of traffic data. Or the occurrence of abnormal pheno...

AI Technical Summary

Problems solved by technology

In recent years, academia has done a lot of research on the recovery of missing traffic data, but how to make full use of spatio-temporal traffic patterns to improve the performance of data interpolation is still the direction of efforts

Images